Wildroot

Search

196 posts · best match first · index holds 129,713 posts · last 36 hours · 1.45 s

Best match combines word and meaning matches. Phrases, hashtags, accounts and websites guide which posts fit; timely queries also favor recent posts. Match labels describe why a post appears, not its quality or accuracy.

Show newest first

  1. @mohammedtahri24@mathstodon.xyzMastodon

    Sprint 31/90 · From perceptron to multilayer network No line \(w \cdot x + b = 0\) separates XOR. Rosenblatt's rule: AND has no miss from epoch 6; XOR ends every epoch on the same weights from epoch 2. Two ReLU units with hand-set weights (Goodfellow et al. §6.1) map (0,1) and (1,0) to one point; then \(h_1 - 2h_2\) gives 0, 1, 1, 0. Gradient descent, 100 seeds: 2 hidden units solve 77, 4 solve 100. Archive: zenodo.org/communities/mt24-le… #MT24Learning #NeuralNetworks #MachineLearning

    zenodo.org

    Has the hashtagAI
    Read post · Mastodon
  2. @earlkmiller.bsky.socialBluesky

    Instead of focusing on single neurons, they make sense of neural activity by chopping each trial at task events and summarizing the whole population. Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens arxiv.org/abs/2610.03001 #neuroscience

    arxiv.org Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens

    Same subjectAI
    Read post · Bluesky
  5. @kromosynth@sigmoid.socialMastodon

    Many of the current #AI “systems point backward, showing us where we have been rather than where we might go. Every answer it gives is a remix of yesterday’s knowledge, polished and repackaged until it feels like something new” - halldoramogensen.substack.com/…

    halldoramogensen.substack.com Infrastructure of Thought

    Same subjectAI
    Read post · Mastodon
  7. @erikahall.bsky.socialBluesky

    "you would have to feed in millions of separate little things every day to equal what a child takes in. And after three years of this kind of business, it still might not have learned to reason or work out its own programs. You ask it to add 2 and 2, and maybe it says 5.” archive.org/details/how_...

    Same subjectAI
    Read post · Bluesky
  10. @ewingt-phd.bsky.socialBluesky

    Can your #brain make new #neurons? www.nature.com/articles/d41... In the 1990s: — Researchers could see cells that had incorporated BrdU, meaning that they had originated from dividing cells — Some were non-neuronal cells, but the team identified others as neurons

    nature.com Can your brain grow new neurons? How researchers are solving a century-old puzzle

    Same subjectScience
    Read post · Bluesky
  11. @schoppik.comBluesky

    If you've ever wondered how the brain *really* keeps things in mind, come let Aaron, Nick & their colleagues in the Nagel lab tell you how the fly does it here: www.nature.com/articles/s41...

    nature.com A split attractor design for rapidly writing a navigational goal

    Same subject
    Read post · Bluesky
  14. @i3suporto.bsky.socialBluesky

    #i3S researchers Mónica Sousa and Ana Rita Costa recently published a paper in the journal 𝘚𝘤𝘪𝘦𝘯𝘤𝘦 𝘈𝘥𝘷𝘢𝘯𝘤𝘦𝘴, in which they outline the workings of new mechanisms that help explain how neurons build and maintain their inner architecture. 📰👀👇 #i3Sresearch #i3Sinnovation #i3Spapers #neurobiology

    tinyurl.com i3S revela como se constrói e mantém o «esqueleto» dos neurónios

    Same subjectScience
    Read post · Bluesky
  15. @ai-firehose.column.socialBluesky

    Flow-of-Thought boosts AI spatial reasoning via visual sketches, scoring 100% in Tetris-like tasks. This framework mimics human mental imagery, linking visual processes to large language models and promising improvements in AI's handling of complex spatial tasks. https://arxiv.org/abs/2610.09746

    arxiv.org Flow-of-Thought: A Framework for Visual Reasoning

    Same subject
    Read post · Bluesky
  17. @neilturkewitz.bsky.socialBluesky

    As @anilseth.bsky.social simply & correctly observes: “The only way to ensure safety is to not build these things in the first place.” I wrote about this in 2021, prompted by a documentary about Anthony Bourdain that employed AI to have him speak words he never said. medium.com/@nturkewitz_...

    Same subjectAI
    Read post · Bluesky
  19. @carlquintanilla.bsky.socialBluesky

    ".. A new poll from The Associated Press-NORC Center for Public Affairs Research finds that most Americans, 64%, think AI is developing 'too fast,' while 27% say its development has been 'about right' and only 8% say it's moving 'too slow.'" @apnews.com apnews.com/article/arti...

    apnews.com Most Americans think artificial intelligence is developing too fast, a new AP-NORC poll finds

    Same subjectAI
    Read post · Bluesky

Search looks through the last 36 hours of public posts for your words, "exact phrases", #hashtags, @handles and websites, and also finds posts about the same thing by meaning. New posts join about every 10 minutes. We only include posts whose authors allow logged-out viewing (Bluesky) or search (Mastodon, indexable accounts), and we re-check Bluesky authors each time we show a page. Likes and follower counts never decide the order. For meaning matches, query text is turned into a fingerprint on Wildroot’s own server (EmbeddingGemma-300M); it is never sent to another service. Wildroot does not save query text to disk. Looking for posts like one you have? Similar posts. How to opt out.